Elemental's RapiHD™ Video Platform is powered by fast, modern graphics processing units (GPUs). This is different from most computer software, which runs on the central processing unit (CPU). We often get asked why we selected the GPU as our hardware platform. The basic answer is straightforward: it is currently the most cost-efficient architecture for high-performance computing. Furthermore, there is a confluence of three major technology trends that have come together to make the time just right to use GPUs for more than just 3D games.

Elemental's RapiHD™ Video Platform is powered by fast, modern graphics processing units (GPUs). This is different from most computer software, which runs on the central processing unit (CPU). We often get asked why we selected the GPU as our hardware platform. The basic answer is straightforward: it is currently the most cost-efficient architecture for high-performance computing. Furthermore, there is a confluence of three major technology trends that have come together to make the time just right to use GPUs for more than just 3D games.

1. Unsurpassed performance, and an unlimited performance trajectory. Semiconductor manufacturers have run into painful physics limitations that have reduced their ability to gain performance through faster clock rates. For example, Intel's top of the line CPUs have run right around 3 GHz for several years now. To increase performance Intel has been forced to add multiple cores -- and Intel has the best manufacturing facilities on the planet. The major GPU makers have had to contend with this problem for longer, and thus migrated to a stream processor architecture several years ago. Today, the highest-performance NVIDIA GPUs have 128 stream processors; ATI tops out at 320 stream processors. This performance chart shows the widening disparity between CPU and GPU horsepower:
   

   

2. At long last, GPUs have gained more programmability. NVIDIA's release of the CUDA platform has created a way to take advantage of GPU horsepower with high-level C code. AMD/ATI has a similar initiative underway called CTM (Close to the Metal), although it is targeted at a significantly lower level than CUDA. Intel's Larrabee project, a high-performance discrete GPU that will go head-to-head with NVIDIA and AMD, is due out in 2009 and will reportedly contain a multitude of x86-based cores -- allowing the use of standard development environments to program the chip. All in all, the recent addition of reasonable programming models for GPUs makes them a good candidate for high-performance applications. At the same time, it doesn't make the task of finding talented developers that can efficiently implement parallel code any easier. Elemental is always hiring parallel processing superstars!
3. Dramatically increased system bandwidth. In the "old days" of PCI and AGP, there was a very fast downlink from the CPU to the GPU. That is, the CPU could deliver data for the GPU to process and then output to the video display. However, the bandwidth for the reverse path -- from the GPU back to the CPU -- was extremely low. The development of PCI Express changed this equation. Now the bandwidth between the GPU and CPU is symmetric, allowing data to be sent to the GPU for analysis and then returned to the host system when processing is complete. This is critical for our application: frames of high-definition video are huge and require a tremendous amount of bandwidth to get schlepped back and forth quickly!

• ‹ previous
• 55 of 56
• next ›